GLM-4.7 Flash

RaisonnementOutils

ZhipuAI's fast and efficient model variant. Optimized for speed while maintaining strong language capabilities.

Identifiant du modèle — à coller dans votre code

z-ai/glm-4.7-flash

Tarifs · par million de tokens

1 Pulse = 1 DA

Entrée10,9 Pulses= 10,9 DA

Sortie72 Pulses= 72 DA

Entrée en cache10,9 Pulses= 10,9 DA

Fenêtre de contexte200KSortie max.: 128K

Capacités

Raisonnement — Réfléchit étape par étape avant de répondre
Outils — Peut appeler vos fonctions / outils

Estimez votre coût

Tokens en entrée Tokens en sortie Requêtes

Coût estimé

Utiliser ce modèle

Créez un compte, rechargez en dinars et appelez-le avec votre clé :

from openai import OpenAI

client = OpenAI(
    base_url="https://dztokens.com/v1",
    api_key="sk-dz-…",
)

reply = client.chat.completions.create(
    model="z-ai/glm-4.7-flash",
    messages=[{"role": "user", "content": "Salam!"}],
)
print(reply.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://dztokens.com/v1",
  apiKey: process.env.DZTOKENS_API_KEY,
});

const reply = await client.chat.completions.create({
  model: "z-ai/glm-4.7-flash",
  messages: [{ role: "user", content: "Salam!" }],
});
console.log(reply.choices[0].message.content);

curl https://dztokens.com/v1/chat/completions \
  -H "Authorization: Bearer $DZTOKENS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-4.7-flash",
    "messages": [{"role": "user", "content": "Salam!"}],
    "stream": true
  }'

from anthropic import Anthropic

client = Anthropic(
    base_url="https://dztokens.com",
    api_key="sk-dz-…",
)

msg = client.messages.create(
    model="z-ai/glm-4.7-flash",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Salam!"}],
)
print(msg.content[0].text)

Créer un compte gratuit Console

Autres modèles Z.ai (GLM)

GLM-5.3Z.ai (GLM)

z-ai/glm-5.3

Z-AI's flagship reasoning model on a 1M-token context. Reasoning is always on, with low, high, and max effort levels, and strong coding and tool-calling.

Entrée125 Pulses

Sortie416 Pulses

Contexte1.05M

GLM-5.2Z.ai (GLM)

z-ai/glm-5.2

Z-AI's latest flagship model for long-horizon tasks. Delivers a substantial leap in long-horizon capability over GLM-5.1 on a solid 1M-token context, with stronger coding and flexible thinking effort.

Entrée135 Pulses

Sortie432 Pulses

Contexte1.05M

GLM-5.1Z.ai (GLM)

z-ai/glm-5.1

Z-AI's next-generation flagship model for agentic engineering. Stronger coding capabilities and state-of-the-art performance on SWE-Bench Pro.

Entrée149 Pulses

Sortie594 Pulses

Contexte205K

GLM-5Z.ai (GLM)

z-ai/glm-5

ZhipuAI's most capable reasoning model with 128K context window. Supports tool calling, web search, and thinking.